INDEX

Explanations

terms related to multiplication and multipliers

oai_token-act-pair · gpt-4o-mini Triggered by @bot

multiply, multiplier, multiplication, multiplicity

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.65

InstanceState

-0.48

存于互联网档案馆

-0.47

Revenir

-0.46

 bahía

-0.45

setContentView

-0.45

Välislingid

-0.45

twimg

-0.44

Scénario

-0.44

Cé

-0.44

POSITIVE LOGITS

 multip

0.75

 multiplication

0.75

 Mult

0.73

 multiply

0.72

Multip

0.68

multiplication

0.68

 Multip

0.68

 multiplier

0.67

 Multiplication

0.67

 mult

0.65

Activations Density 0.032%

terms related to multiplication and multipliers

multiply, multiplier, multiplication, multiplicity

No Comments

No Known Activations